Communitygithub.com

Video Prompting Guide / 视频提示词指南

编写有效AI视频生成提示词的最佳实践和技巧。涵盖 Veo、Seedance、Wan、Grok、Kling、Runway、Pika、Sora 等平台的提示策略。

视频提示词指南 是什么?

该技能(skill)提供了为 AI 视频生成模型编写高质量提示词的系统性方法和最佳实践。它涵盖了 Veo、Seedance、Wan、Grok、Kling、Runway、Pika、Sora 等主流平台的独特提示策略。技能的核心是一套可复用的“镜头类型 + 主体 + 动作 + 场景 + 光照 + 风格 + 技术参数”的结构化公式,并配有丰富的示例和对照表(如镜头类型、相机运动、光照关键词、风格关键词)。此外,它还详细列出了常见错误(如提示词过于模糊或风格冲突)以及针对不同模型(如 Google Veo、Seedance)的调优技巧,例如 Seedance 擅长处理舞蹈动作和人形运动。该技能主要面向使用 inference.sh CLI(belt)的用户,但其中的通用原则适用于任何 AI 视频生成工具。通过遵循该指南,用户可以大幅提升视频生成的质量与一致性,获得更专业、更可预测的视觉效果。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/101-skills/skills/video-prompting-guide

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

预览

来自技能 README

视频提示词指南

文档

安装 belt CLI 技能: npx skills add belt-sh/cli

视频提示词指南

通过 inference.sh 编写有效 AI 视频生成提示词的最佳实践。

视频提示词指南

快速开始

需要 inference.sh CLI (belt)。安装说明

belt login

# 结构良好的视频提示词
belt app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic tracking shot of a red sports car driving through Tokyo at night, neon lights reflecting on wet streets, rain falling, 4K, shallow depth of field"
}'

提示词结构公式

[镜头类型] + [主体] + [动作] + [场景] + [光照] + [风格] + [技术参数]

示例分解

"Slow motion close-up of coffee being poured into a white ceramic cup,
steam rising, morning sunlight streaming through window, warm color grading,
cinematic, 4K, shallow depth of field"
  • 镜头类型:慢动作特写
  • 主体:咖啡
  • 动作:被倒出
  • 场景:白色陶瓷杯、窗户
  • 光照:晨光
  • 风格:暖色调、电影感
  • 技术参数:4K、浅景深

镜头类型

镜头类型描述用途
广角镜头 (Wide shot)展示整个场景确立地点
中景镜头 (Medium shot)腰部以上的取景对话、动作
特写镜头 (Close-up)面部或细节情感、产品细节
极特写镜头 (Extreme close-up)单一特征戏剧性、质感
航拍镜头 (Aerial shot)俯拍视角风景、规模
低角度镜头 (Low angle)相机向上看力量、宏大
高角度镜头 (High angle)相机向下看脆弱感
荷兰角镜头 (Dutch angle)镜头倾斜不安、紧张
主观镜头 (POV shot)第一人称视角沉浸感

相机运动

运动方式描述效果
跟拍 (Tracking shot)相机跟随主体动态、引人入胜
推拉镜头 (Dolly in/out)相机向主体移动/远离聚焦、揭示
横摇 (Pan)水平旋转环顾场景
纵摇 (Tilt)垂直旋转揭示高度
吊臂镜头 (Crane shot)垂直+水平戏剧性揭示
手持镜头 (Handheld)轻微晃动真实感、紧迫感
斯坦尼康 (Steadicam)平滑跟随专业、电影感
变焦 (Zoom)镜头变焦拉近/拉远快速聚焦变化
静态 (Static)无运动沉思、稳定

光照关键词

关键词效果
Golden hour温暖、柔和、浪漫
Blue hour凉爽、忧郁、黄昏
High key明亮、阴影最少
Low key黑暗、戏剧性阴影
Rim lighting主体被光勾勒轮廓
Backlit光从主体后方照射
Soft lighting柔和、迷人
Hard lighting锐利阴影、高对比度
Neon多彩、都市、赛博朋克
Natural lighting真实、纪录片风格

风格关键词

电影风格

cinematic, film grain, anamorphic lens, letterbox,
shallow depth of field, bokeh, 35mm film,
color grading, theatrical

视觉美学

minimalist, maximalist, vintage, retro, futuristic,
cyberpunk, steampunk, noir, pastel, vibrant,
muted colors, high contrast, desaturated

质量关键词

4K, 8K, high resolution, photorealistic,
hyperrealistic, ultra detailed, professional,
broadcast quality, HDR

按使用场景的提示词示例

产品演示

belt app run google/veo-3-1-fast --input '{
  "prompt": "Smooth tracking shot around a sleek smartphone on a white pedestal, soft studio lighting, product photography style, reflections on surface, 4K, shallow depth of field"
}'

自然纪录片

belt app run google/veo-3 --input '{
  "prompt": "Slow motion extreme close-up of a hummingbird hovering at a red flower, wings in motion blur, shallow depth of field, golden hour lighting, National Geographic style"
}'

都市生活

belt app run google/veo-3 --input '{
  "prompt": "Tracking shot following a cyclist through busy city streets, morning rush hour, natural lighting, handheld camera feel, documentary style, authentic and candid"
}'

美食内容

belt app run bytedance/seedance-2-0 --input '{
  "prompt": "Close-up of chocolate sauce being drizzled over ice cream, slow motion, steam rising, soft lighting, food photography style, appetizing, commercial quality",
  "generate_audio": true
}'

科技/未来感

belt app run xai/grok-imagine-video --input '{
  "prompt": "Futuristic control room with holographic displays, camera slowly pans across the space, blue and cyan lighting, sci-fi atmosphere, Blade Runner aesthetic, 4K",
  "duration": 5
}'

常见错误避免

错误问题更好的方式
过于模糊"一段不错的视频"明确镜头、主体、风格
过于复杂多个场景每次提示一个场景
没有运动静态描述包含相机运动或主体动作
风格冲突"极简主义 极繁主义"选择一种美学
没有光照未定义氛围指定光照条件

模型特定技巧

Google Veo

  • 擅长写实、电影感内容
  • 支持音频生成(Veo 3+)
  • 最好使用详细、专业的提示词
  • 3.1 版本支持帧插值

Seedance

  • 擅长舞蹈和人物运动
  • 支持首帧控制
  • 适合一致的角色动作
  • 与参考图像配合良好

Wan 2.5

  • 最适合图像到视频
  • 自然动画化静态图像
  • 良好的运动预测
  • 适用于任何图像风格

Grok

  • 良好的通用视频生成
  • 可配置时长(5-10s)
  • 创意解读
  • 适用于抽象概念

工作流程:迭代提示

# 1. 从基础提示词开始
belt app run google/veo-3-1-fast --input '{
  "prompt": "A woman walking through a forest"
}'

# 2. 增加具体性
belt app run google/veo-3-1-fast --input '{
  "prompt": "Medium tracking shot of a woman in a red dress walking through an autumn forest"
}'

# 3. 增加风格和技术细节
belt app run google/veo-3-1-fast --input '{
  "prompt": "Cinematic medium tracking shot of a woman in a flowing red dress walking through an autumn forest, golden hour sunlight filtering through leaves, shallow depth of field, film grain, 4K"
}'

相关技能

# 生成视频
npx skills add inference-sh/skills@ai-video-generation

# Google Veo 专用
npx skills add inference-sh/skills@google-veo

# 生成图像(用于图像到视频)
npx skills add inference-sh/skills@ai-image-generation

# 通用提示工程
npx skills add inference-sh/skills@prompt-engineering

# 完整平台技能
npx skills add inference-sh/skills@infsh-cli

浏览所有视频应用:belt app store --category video

文档

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Download YouTube videos, extract/proofread/translate subtitles, and render them onto video. Use whenever the user asks to download a YouTube video with subtitles, translate video subtitles to Chinese, add subtitles/burn subtitles to a video, or do ASR transcription on video audio. Covers the full pipeline: video download → subtitle extraction → proofreading → translation → SRT generation → subtitle rendering. Also use for "下载视频加字幕", "视频翻译字幕", "把字幕烧录到视频中". For pure subtitle file creation without rendering (just SRT output), this skill handles that too — stop before Phase 5.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

相关技能